Abstract Domain adaptation in person re-identification (re-ID) has always been a
challenging task. In this work, we explore how to harness the similar natural characteristics …

Most existing person re-identification (re-id) methods require supervised model learning
from a separate large set of pairwise labelled training data for every single camera pair. This …

Person re-identification (re-ID) has become increasingly popular in the community due to its
application and research significance. It aims at spotting a person of interest in other …

We focus on the one-shot learning for video-based person re-Identification (re-ID).
Unlabeled tracklets for the person re-ID tasks can be easily obtained by pre-processing …

Most existing person re-identification (re-id) methods focus on learning the optimal distance
metrics across camera views. Typically a person's appearance is represented using features …

Person re-identification is an important technique towards automatic search of a person's
presence in a surveillance video. Two fundamental problems are critical for person re …

Traditional person re-identification (re-id) methods perform poorly under changing
illuminations. This situation can be addressed by using dual-cameras that capture visible …

Most existing person re-identification (re-id) methods rely on supervised model learning on
per-camera-pair manually labelled pairwise training data. This leads to poor scalability in …

While discriminative local features have been shown effective in solving the person re-
identification problem, they are limited to be trained on fully pairwise labelled data which is …